Position and orientation measurement for large-size workpiece based on binocular vision
Position and orientation measurement for large-size workpiece based on binocular vision
复制标题
DOI：
10.1117/12.871802
复制
发表时间：
2010-11
期刊：
影响因子：
--
通讯作者：
Fuguo Liu;Xiaoping Lou;Naiguang Lv;P. Sun
中科院分区：
文献类型：
--
作者：
Fuguo Liu;Xiaoping Lou;Naiguang Lv;P. Sun
基于自由曲面零件的CAD模型，提出了一种无接触自动获取零件位置和姿态的方法。该方法包括两个步骤。第一步是基于表面特征的粗略定位，得到零件与CAD模型的近似对应关系。第二步是精细定位。该算法通过对CAD模型进行曲面网格剖分，在CAD曲面上搜索与光点最近的点，从而实现对光点的分割。在这一步中使用了迭代最近点算法，该算法获得了零件和CAD模型之间的精确对应。实验结果表明，该方法是有效的，具有较强的鲁棒性。
Based on the CAD model of the free-form surface workpiece, an automatic method to obtain the position and orientation of the workpiece without contact is proposed. The method consists of two steps. The first step is rough localization which gets the approximate correspondence between workpiece and CAD model based on surface features. The second step is fine localization. It is achieved by searching the nearest point on the CAD surface to the light dot by gridsubdivide surface of CAD model. ICP (iterative closest point) algorithm that obtains precise correspondences between the workpiece and the CAD model is used for this step. Experiments were carried out and the results show that the method is efficient and robust.